Analysis of flash droughts in China using machine learning

Zhang, Linqi; Liu, Yi; Ren, Liliang; Teuling, Adriaan J.; Zhu, Ye; Wei, Linyong; Zhang, Linyan; Jiang, Shanhu; Yang, Xiaoli; Fang, Xiuqin; Yin, Hang

doi:https://doi.org/10.5194/hess-26-3241-2022

Articles | Volume 26, issue 12

https://doi.org/10.5194/hess-26-3241-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-26-3241-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 26, issue 12

Research article

|

24 Jun 2022

Research article |

| 24 Jun 2022

Analysis of flash droughts in China using machine learning

Linqi Zhang, Yi Liu, Liliang Ren, Adriaan J. Teuling, Ye Zhu, Linyong Wei, Linyan Zhang, Shanhu Jiang, Xiaoli Yang, Xiuqin Fang, and Hang Yin

Data sets

ERA Interim, Daily European Center for Medium-Range Weather Forecast https://apps.ecmwf.int/datasets/data/interim-full-daily/levtype=sfc/

ERA5-Land hourly data from 1950 to present European Center for Medium-Range Weather Forecast https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-land

Short summary

In this study, three machine learning methods displayed a good detection capacity of flash droughts. The RF model was recommended to estimate the depletion rate of soil moisture and simulate flash drought by considering the multiple meteorological variable anomalies in the adjacent time to drought onset. The anomalies of precipitation and potential evapotranspiration exhibited a stronger synergistic but asymmetrical effect on flash droughts compared to slowly developing droughts.